Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (readOnly, idempotent, non-destructive), and the description goes well beyond them: it caps results (max 50), discloses the total match count, and explains the tricky currency semantics of in_latest_scan, last_checked_at, and verdict_since, including the non-obvious caveat that verdict_since can span unmeasured weeks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and usage are front-loaded, which is good, but the final block repeats the in_latest_scan/last_checked_at relationship twice and spends five lines on verdict_since semantics that could be compressed. The core call information is buried under an extended caveat paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly describes the return shape (up to limit endpoints with latest verdict, plus total match count) and supplies the data-currency semantics an agent needs to interpret rows. Minor omissions: no pagination guidance and incomplete sort/limit defaults.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry all parameter meaning and largely does: query (host or URL substring), limit (max 50), network (with example values like eip155:8453), and sort=price for cheapest-first. Gaps remain — the default limit of 25, the default empty sort, and other valid sort values are not documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a precise verb and resource: search the catalogue by host or URL substring. It also frames its own role ('Use this first when you do not know the exact resource URL'), which implicitly separates it from exact-lookup siblings, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States a clear when-to-use condition ('Use this first when you do not know the exact resource URL') and notes the optional network filter and sort=price shortcut. It stops short of naming alternatives or stating when-not to use it (e.g. when you already have an exact URL, use X instead).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.